# Improving Reverberant Speech Training Using Diffuse Acoustic Simulation

arXiv: https://arxiv.org/abs/1907.03988 · HTML: https://mlsanity.com/paper/1907.03988/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [FAST-RIR: Fast neural diffuse room impulse response generator](https://mlsanity.com/paper/2110.04057/) (2021)
- [MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes](https://mlsanity.com/paper/2205.09248/) (2022)
- [Measuring Acoustics with Collaborative Multiple Agents](https://mlsanity.com/paper/2310.05368/) (2023)
- [Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes](https://mlsanity.com/paper/2302.02809/) (2023)
- [SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios](https://mlsanity.com/paper/2410.01481/) (2024)
- [Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation](https://mlsanity.com/paper/2212.05360/) (2022)
- [Bayesian inference and neural estimation of acoustic wave propagation](https://mlsanity.com/paper/2305.17749/) (2023)
- [SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field](https://mlsanity.com/paper/2406.11006/) (2024)
- [PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation](https://mlsanity.com/paper/2607.23293/) (2026)

## Abstract (arXiv)

We present an efficient and realistic geometric acoustic simulation approach for generating and augmenting training data in speech-related machine learning tasks. Our physically-based acoustic simulation method is capable of modeling occlusion, specular and diffuse reflections of sound in complicated acoustic environments, whereas the classical image method can only model specular reflections in simple room settings. We show that by using our synthetic training data, the same neural networks gain significant performance improvement on real test sets in far-field speech recognition by 1.58% and keyword spotting by 21%, without fine-tuning using real impulse responses.